44 lines
1.0 KiB
JSON
44 lines
1.0 KiB
JSON
{
|
|
"_name_or_path": "CohereForAI/c4ai-command-r-v01",
|
|
"architectures": [
|
|
"CohereForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 5,
|
|
"eos_token_id": 255001,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 8192,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 22528,
|
|
"layer_norm_eps": 1e-05,
|
|
"logit_scale": 0.0625,
|
|
"max_position_embeddings": 8192,
|
|
"model_max_length": 131072,
|
|
"model_type": "cohere",
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 64,
|
|
"pad_token_id": 0,
|
|
"pretraining_tp": 1,
|
|
"quantization_config": {
|
|
"bits": 4,
|
|
"checkpoint_format": "gptq",
|
|
"damp_percent": 0.01,
|
|
"desc_act": true,
|
|
"group_size": 128,
|
|
"model_file_base_name": null,
|
|
"model_name_or_path": null,
|
|
"quant_method": "gptq",
|
|
"static_groups": false,
|
|
"sym": true,
|
|
"true_sequential": true
|
|
},
|
|
"rope_theta": 8000000.0,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.40.0",
|
|
"use_cache": true,
|
|
"use_qk_norm": false,
|
|
"vocab_size": 256000
|
|
}
|